PLS-ANN based classification model for oral submucous fibrosis and oral carcinogenesis

Artificial Intelligence's Use in the Diagnosis of Mouth Ulcers: A Systematic Review

Artificial intelligence (AI) has been cited as being helpful in the diagnosis of diseases, the prediction of prognoses, and the development of patient-specific therapeutic strategies. AI can help dentists, in particular, when they need to make important judgments quickly. It can eliminate human mistakes in making decisions, resulting in superior and consistent medical treatment while lowering the workload on dentists. The existing studies relevant to the study and application of AI in the diagnosis of various forms of mouth ulcers are reviewed in this work. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) standards were followed in the preparation of the review. There were no rule violations, with the significant exception of the use of a better search method that led to more accurate findings. Using search terms mainly such as AI, oral health, oral ulcers, oral herpes simplex, oral lichen planus, pemphigus vulgaris, recurrent aphthous ulcer (RAU), oral cancer, premalignant and malignant disorders, etc., a comprehensive search was carried out in the reliable sources of literature, namely PubMed, Scopus, Embase, Web of Science, Ovid, Global Health, and PsycINFO. For all papers, exhaustive searches were done using inclusion criteria as well as exclusion criteria between June 28, 2018, and June 28, 2023. An AI framework for the automatic categorization of oral ulcers from oral clinical photographs was developed by the authors, and it performed satisfactorily. The newly designed AI model works better than the current convolutional neural network image categorization techniques and shows a fair level of precision in the classification of oral ulcers. However, despite being useful for identifying oral ulcers, the suggested technique needs a broader set of data for validation and training purposes before being used in clinical settings. Automated OCSCC identification using a deep learning-based technique is a quick, harmless, affordable, and practical approach to evaluating the effectiveness of cancer treatment. The categorization and identification of RAU lesions through the use of non-intrusive oral pictures using the previously developed ResNet50 and YOLOV algorithms demonstrated better accuracy as well as adequate potential for the future, which could be helpful in clinical practice. Moreover, the most reliable projections for the likelihood of the presence or absence of RAU were made by the optimized neural network. The authors also discovered variables associated with RAU that might be used as input information to build artificial neural networks that anticipate RAU.

Machine learning in point-of-care automated classification of oral potentially malignant and malignant disorders: a systematic review and meta-analysis

Machine learning (ML) algorithms are becoming increasingly pervasive in the domains of medical diagnostics and prognostication, afforded by complex deep learning architectures that overcome the limitations of manual feature extraction. In this systematic review and meta-analysis, we provide an update on current progress of ML algorithms in point-of-care (POC) automated diagnostic classification systems for lesions of the oral cavity. Studies reporting performance metrics on ML algorithms used in automatic classification of oral regions of interest were identified and screened by 2 independent reviewers from 4 databases. Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were followed. 35 studies were suitable for qualitative synthesis, and 31 for quantitative analysis. Outcomes were assessed using a bivariate random-effects model following an assessment of bias and heterogeneity. 4 distinct methodologies were identified for POC diagnosis: (1) clinical photography; (2) optical imaging; (3) thermal imaging; (4) analysis of volatile organic compounds. Estimated AUROC across all studies was 0.935, and no difference in performance was identified between methodologies. We discuss the various classical and modern approaches to ML employed within identified studies, and highlight issues that will need to be addressed for implementation of automated classification systems in screening and early detection.

Machine-Learning Applications in Oral Cancer: A Systematic Review

Over the years, several machine-learning applications have been suggested to assist in various clinical scenarios relevant to oral cancer. We offer a systematic review to identify, assess, and summarize the evidence for reported uses in the areas of oral cancer detection and prevention, prognosis, pre-cancer, treatment, and quality of life. The main algorithms applied in the context of oral cancer applications corresponded to SVM, ANN, and LR, comprising 87.71% of the total published articles in the field. Genomic, histopathological, image, medical/clinical, spectral, and speech data were used most often to predict the four areas of application found in this review. In conclusion, our study has shown that machine-learning applications are useful for prognosis, diagnosis, and prevention of potentially malignant oral lesions (pre-cancer) and therapy. Nevertheless, we strongly recommended the application of these methods in daily clinical practice.

Non-invasive imaging of oral potentially malignant and malignant lesions: A systematic review and meta-analysis

Non-invasive (NI) imaging techniques have been developed to overcome the limitations of invasive biopsy procedures, which is the gold standard in diagnosis of oral dysplasia and Oral Squamous Cell Carcinoma (OSCC). This systematic review and meta- analysis was carried out with an aim to investigate the efficacy of the NI-imaging techniques in the detection of dysplastic oral potentially malignant disorders (OPMDs) and OSCC. Records concerned in the detection of OPMDs, Oral Cancer were identified through search in PubMed, Science direct, Cochrane Library electronic database (January 2000 to October 2020) and additional manual searches. Out of 529 articles evaluated for eligibility, 56 satisfied the pre-determined inclusion criteria, including 13 varying NI-imaging techniques. Meta-analysis consisted 44 articles, wherein majority of the studies reported Autofluorescence (AFI-38.6%) followed by Chemiluminescence (CHEM), Narrow Band Imaging (NBI) (CHEM, NBI-15.9%), Fluorescence Spectroscopy (FS), Diffuse Reflectance Spectroscopy (DRS), (FS, DRS-13.6%) and 5aminolevulinic acid induced protoporphyrin IX fluorescence (5ALA induced PPIX- 6.8%). Higher sensitivities (Sen) and specificities (Spe) were obtained using FS (Sen:74%, Spe:96%, SAUC=0.98), DRS (Sen:79%, Spe:86%, SAUC = 0.91) and 5 ALA induced PPIX (Sen:91%, Spe:78%, SAUC = 0.98) in the detection of dysplastic OPMDs from non-dysplastic lesions(NDLs). AFI, FS, DRS, NBI showed higher sensitivities and SAUC (>90%) in differentiating OSCC from NDLs. Analysed NI-imaging techniques suggests the higher accuracy levels in the diagnosis of OSCC when compared to dysplastic OPMDs. 5 ALA induced PPIX, DRS and FS showed evidence of superior accuracy levels in differentiation of dysplastic OPMDs from NDLs, however results need to be validated in a larger number of studies.

Role of Artificial Intelligence in the Early Diagnosis of Oral Cancer. A Scoping Review

The early diagnosis of cancer can facilitate subsequent clinical patient management. Artificial intelligence (AI) has been found to be promising for improving the diagnostic process. The aim of the present study is to increase the evidence on the application of AI to the early diagnosis of oral cancer through a scoping review. A search was performed in the PubMed, Web of Science, Embase and Google Scholar databases during the period from January 2000 to December 2020, referring to the early non-invasive diagnosis of oral cancer based on AI applied to screening. Only accessible full-text articles were considered. Thirty-six studies were included on the early detection of oral cancer based on images (photographs (optical imaging and enhancement technology) and cytology) with the application of AI models. These studies were characterized by their heterogeneous nature. Each publication involved a different algorithm with potential training data bias and few comparative data for AI interpretation. Artificial intelligence may play an important role in precisely predicting the development of oral cancer, though several methodological issues need to be addressed in parallel to the advances in AI techniques, in order to allow large-scale transfer of the latter to population-based detection protocols.

Current Insights into Oral Cancer Diagnostics

Oral cancer is one of the most common head and neck malignancies and has an overall 5-year survival rate that remains below 50%. Oral cancer is generally preceded by oral potentially malignant disorders (OPMDs) but determining the risk of OPMD progressing to cancer remains a difficult task. Several diagnostic technologies have been developed to facilitate the detection of OPMD and oral cancer, and some of these have been translated into regulatory-approved in vitro diagnostic systems or medical devices. Furthermore, the rapid development of novel biomarkers, electronic systems, and artificial intelligence may help to develop a new era where OPMD and oral cancer are detected at an early stage. To date, a visual oral examination remains the routine first-line method of identifying oral lesions; however, this method has certain limitations and as a result, patients are either diagnosed when their cancer reaches a severe stage or a high-risk patient with OPMD is misdiagnosed and left untreated. The purpose of this article is to review the currently available diagnostic methods for oral cancer as well as possible future applications of novel promising technologies to oral cancer diagnosis. This will potentially increase diagnostic options and improve our ability to effectively diagnose and treat oral cancerous-related lesions.

Machine learning in oral squamous cell carcinoma: Current status, clinical concerns and prospects for future-A systematic review

BACKGROUND

Oral cancer can show heterogenous patterns of behavior. For proper and effective management of oral cancer, early diagnosis and accurate prediction of prognosis are important. To achieve this, artificial intelligence (AI) or its subfield, machine learning, has been touted for its potential to revolutionize cancer management through improved diagnostic precision and prediction of outcomes. Yet, to date, it has made only few contributions to actual medical practice or patient care.

OBJECTIVES

This study provides a systematic review of diagnostic and prognostic application of machine learning in oral squamous cell carcinoma (OSCC) and also highlights some of the limitations and concerns of clinicians towards the implementation of machine learning-based models for daily clinical practice.

DATA SOURCES

We searched OvidMedline, PubMed, Scopus, Web of Science, and Institute of Electrical and Electronics Engineers (IEEE) databases from inception until February 2020 for articles that used machine learning for diagnostic or prognostic purposes of OSCC.

ELIGIBILITY CRITERIA

Only original studies that examined the application of machine learning models for prognostic and/or diagnostic purposes were considered.

DATA EXTRACTION

Independent extraction of articles was done by two researchers (A.R. & O.Y) using predefine study selection criteria. We used the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) in the searching and screening processes. We also used Prediction model Risk of Bias Assessment Tool (PROBAST) for assessing the risk of bias (ROB) and quality of included studies.

RESULTS

A total of 41 studies were published to have used machine learning to aid in the diagnosis/or prognosis of OSCC. The majority of these studies used the support vector machine (SVM) and artificial neural network (ANN) algorithms as machine learning techniques. Their specificity ranged from 0.57 to 1.00, sensitivity from 0.70 to 1.00, and accuracy from 63.4 % to 100.0 % in these studies. The main limitations and concerns can be grouped as either the challenges inherent to the science of machine learning or relating to the clinical implementations.

CONCLUSION

Machine learning models have been reported to show promising performances for diagnostic and prognostic analyses in studies of oral cancer. These models should be developed to further enhance explainability, interpretability, and externally validated for generalizability in order to be safely integrated into daily clinical practices. Also, regulatory frameworks for the adoption of these models in clinical practices are necessary.

The contribution of artificial intelligence to reducing the diagnostic delay in oral cancer

Oral cancer (OC) is the sixth most commonly reported malignant disease globally, with high rates of disease-related morbidity and mortality due to advanced loco-regional stage at diagnosis. Early detection and prompt treatment offer the best outcomes to patients, yet the majority of OC lesions are detected at late stages with 45% survival rate for 2 years. The primary cause of poor OC outcomes is unavailable or ineffective screening and surveillance at the local point-of-care level, leading to delays in specialist referral and subsequent treatment. Lack of adequate awareness of OC among the public and professionals, and barriers to accessing health care services in a timely manner also contribute to delayed diagnosis. As image analysis and diagnostic technologies are evolving, various artificial intelligence (AI) approaches, specific algorithms and predictive models are beginning to have a considerable impact in improving diagnostic accuracy for OC. AI based technologies combined with intraoral photographic images or optical imaging methods are under investigation for automated detection and classification of OC. These new methods and technologies have great potential to improve outcomes, especially in low-resource settings. Such approaches can be used to predict oral cancer risk as an adjunct to population screening by providing real-time risk assessment. The objective of this study is to (1) provide an overview of components of delayed OC diagnosis and (2) evaluate novel AI based approaches with respect to their utility and implications for improving oral cancer detection.

Anatomy-Based Algorithms for Detecting Oral Cancer Using Reflectance and Fluorescence Spectroscopy

Objective

We used reflectance and fluorescence spectroscopy to noninvasively and quantitatively distinguish benign from dysplastic/malignant oral lesions. We designed diagnostic algorithms to account for differences in the spectral properties among anatomic sites (gingiva, buccal mucosa, etc).

Methods

In vivo reflectance and fluorescence spectra were collected from 71 patients with oral lesions. The tissue was then biopsied and the specimen evaluated by histopathology. Quantitative parameters related to tissue morphology and biochemistry were extracted from the spectra. Diagnostic algorithms specific for combinations of sites with similar spectral properties were developed.

Results

Discrimination of benign from dysplastic/malignant lesions was most successful when algorithms were designed for individual sites (area under the receiver operator characteristic curve [ROC-AUC], 0.75 for the lateral surface of the tongue) and was least accurate when all sites were combined (ROC-AUC, 0.60). The combination of sites with similar spectral properties (floor of mouth and lateral surface of the tongue) yielded an ROC-AUC of 0.71.

Conclusions

Accurate spectroscopic detection of oral disease must account for spectral variations among anatomic sites. Anatomy-based algorithms for single sites or combinations of sites demonstrated good diagnostic performance in distinguishing benign lesions from dysplastic/malignant lesions and consistently performed better than algorithms developed for all sites combined.

Accuracy of autofluorescence in diagnosing oral squamous cell carcinoma and oral potentially malignant disorders: a comparative study with aero-digestive lesions

Presently, various studies had investigated the accuracy of autofluorescence in diagnosing oral squamous cell carcinoma (OSCC) and oral potentially malignant disorders (OPMD) with diverse conclusions. This study aimed to assess its accuracy for OSCC and OPMD and to investigate its applicability in general dental practice. After a comprehensive literature search, a meta-analysis was conducted to calculate the pooled diagnostic indexes of autofluorescence for premalignant lesions (PML) and malignant lesions (ML) of the oral cavity, lung, esophagus, stomach and colorectum and to compute indexes regarding the detection of OSCC aided by algorithms. Besides, a u test was performed. Twenty-four studies detecting OSCC and OPMD in 2761 lesions were included. This demonstrated that the overall accuracy of autofluorescence for OSCC and OPMD was superior to PML and ML of the lung, esophagus and stomach, slightly inferior to the colorectum. Additionally, the sensitivity and specificity for OSCC and OPMD were 0.89 and 0.8, respectively. Furthermore, the specificity could be remarkably improved by additional algorithms. With relatively high accuracy, autofluorescence could be potentially applied as an adjunct for early diagnosis of OSCC and OPMD. Moreover, approaches such as algorithms could enhance its specificity to ensure its efficacy in primary care.

Autofluorescence based diagnostic techniques for oral cancer

Oral cancer is one of the most common cancers worldwide. Despite of various advancements in the treatment modalities, oral cancer mortalities are more, particularly in developing countries like India. This is mainly due to the delay in diagnosis of oral cancer. Delay in diagnosis greatly reduces prognosis of the treatment and also cause increased morbidity and mortality rates. Early diagnosis plays a key role in effective management of oral cancer. A rapid diagnostic technique can greatly aid in the early diagnosis of oral cancer. Now a day's many adjunctive oral cancer screening techniques are available for the early diagnosis of cancer. Among these, autofluorescence based diagnostic techniques are rapidly emerging as a powerful tool. These techniques are broadly discussed in this review.

Cancer prediction based on radical basis function neural network with particle swarm optimization

This paper addresses cancer prediction based on radial basis function neural network optimized by particle swarm optimization. Today, cancer hazard to people is increasing, and it is often difficult to cure cancer. The occurrence of cancer can be predicted by the method of the computer so that people can take timely and effective measures to prevent the occurrence of cancer. In this paper, the occurrence of cancer is predicted by the means of Radial Basis Function Neural Network Optimized by Particle Swarm Optimization. The neural network parameters to be optimized include the weight vector between network hidden layer and output layer, and the threshold of output layer neurons. The experimental data were obtained from the Wisconsin breast cancer database. A total of 12 experiments were done by setting 12 different sets of experimental result reliability. The findings show that the method can improve the accuracy, reliability and stability of cancer prediction greatly and effectively.

Tissue discrimination by uncorrected autofluorescence spectra: a proof-of-principle study for tissue-specific laser surgery

Laser surgery provides a number of advantages over conventional surgery. However, it implies large risks for sensitive tissue structures due to its characteristic non-tissue-specific ablation. The present study investigates the discrimination of nine different ex vivo tissue types by using uncorrected (raw) autofluorescence spectra for the development of a remote feedback control system for tissue-selective laser surgery. Autofluorescence spectra (excitation wavelength 377 ± 50 nm) were measured from nine different ex vivo tissue types, obtained from 15 domestic pig cadavers. For data analysis, a wavelength range between 450 nm and 650 nm was investigated. Principal Component Analysis (PCA) and Quadratic Discriminant Analysis (QDA) were used to discriminate the tissue types. ROC analysis showed that PCA, followed by QDA, could differentiate all investigated tissue types with AUC results between 1.00 and 0.97. Sensitivity reached values between 93% and 100% and specificity values between 94% and 100%. This ex vivo study shows a high differentiation potential for physiological tissue types when performing autofluorescence spectroscopy followed by PCA and QDA. The uncorrected autofluorescence spectra are suitable for reliable tissue discrimination and have a high potential to meet the challenges necessary for an optical feedback system for tissue-specific laser surgery.

Evaluation by fluorescence spectroscopy of the most appropriate renal region for obtaining biopsies: a study in the rat

INTRODUCTION

Renal puncture biopsies are directed at the lower poles of the organ to decrease the risk of hemorrhage and complications.

OBJECTIVES

To evaluate by fluorescence spectroscopy (FS) the most appropriate renal region (in terms of metabolic changes) to obtain a biopsy.

MATERIALS AND METHODS

The kidneys of 33 Rattus norvegicus rats were submitted to FS detection in the upper and lower poles and in the middle third. Excitations were generated with lasers at wavelengths of 408, 442, and 532 nm. Animals were divided at random into groups of warm ischemia (30, 60, and 120 minutes), whose kidneys were again analyzed by FS, as well as after 5 minutes of reperfusion using the same excitation beams in the same renal regions. Then the kidneys underwent histologic preparation and examination.

RESULTS

The middle third area of the rat's kidneys proved to be significantly more sensitive to ischemic and reperfusion changes than the renal poles, as determined by FS (P < .001).

CONCLUSIONS

The middle third of the kidney was the most appropriate site for a renal biopsy to monitor a transplanted organ.

Comparative evaluation of the diagnostic performance of autofluorescence and diffuse reflectance in oral cancer detection: a clinical study

Autofluorescence (AF) and diffuse reflectance (DR) spectroscopic techniques have shown good diagnostic accuracies for noninvasive detection of oral cavity cancer. In the present study, AF and DR spectra recorded in vivo from the same set of sites in 65 patients were analyzed using Principal component analysis (PCA) and linear discriminant analysis (LDA). The effectiveness of these two techniques was assessed by comparison with gold standard and their discrimination efficiency was determined from the area under the receiver operator characteristic (AUC-ROC) curve. Analysis using a DR technique shows a higher AUC-ROC of 0.991 as against 0.987 for AF spectral data.

Comparative study of protoporphyrin IX fluorescence image enhancement methods to improve an optical imaging system for oral cancer detection

Optoelectronics techniques to induce protoporphyrin IX fluorescence with topically applied 5-aminolevulinic acid on the oral mucosa have been developed to noninvasively detect oral cancer. Fluorescence imaging enables wide-area screening for oral premalignancy, but the lack of an adequate fluorescence enhancement method restricts the clinical imaging application of these techniques. This study aimed to develop a reliable fluorescence enhancement method to improve PpIX fluorescence imaging systems for oral cancer detection. Three contrast features, red-green-blue reflectance difference, R∕B ratio, and R∕G ratio, were developed first based on the optical properties of the fluorescence images. A comparative study was then carried out with one negative control and four biopsy confirmed clinical cases to validate the optimal image processing method for the detection of the distribution of malignancy. The results showed the superiority of the R∕G ratio in terms of yielding a better contrast between normal and neoplastic tissue, and this method was less prone to errors in detection. Quantitative comparison with the clinical diagnoses in the four neoplastic cases showed that the regions of premalignancy obtained using the proposed method accorded with the expert's determination, suggesting the potential clinical application of this method for the detection of oral cancer.

[Autofluorescence for the detection of potentially malignant and malignant lesions of the oral cavity lining]

INTRODUCTION

The sensitivity of visual examination for the diagnosis of oral cancers is estimated at 85% and its specificity at 97%. However, it is likely that numerous lesions remain undetected. The objective of this article was to review literature on the contribution of tissular autofluorescence to detect potentially malignant and malignant lesions of the oral cavity.

MATERIAL AND METHOD

The Medline database was consulted using the following keywords: fluorescence and cancer; autofluorescence and cancer; fluorescence and oral cancer; autofluorescence and oral cancer; Velscope(®) and oral cancer. Only original articles and clinical case reports on the oral cavity published in English since 1999 were considered.

RESULTS

Twenty-three publications were analyzed. Twelve studies concerned spectroscopy and 14 direct autofluorescence. The specificity of AF ranged between 75 and 100% in spectroscopy and between 39 and 100% in direct vision. The sensibility of the AF varied between 78 and 100% in spectroscopy and between 50 and 100% in direct vision.

DISCUSSION

The variability of results may be explained by selection bias. The main contribution of fluorescence is to highlight oral mucous membrane lesions and to help physicians to better locate them. The lack of AF specificity supports the contribution of histological examination which remains the reference examination for the diagnosis of potentially malignant lesions and cancers of the oral cavity.

Anatomy-Based Algorithms for Detecting Oral Cancer Using Reflectance and Fluorescence Spectroscopy

Objectives:

We used reflectance and fluorescence spectroscopy to noninvasively and quantitatively distinguish benign from dysplastic/malignant oral lesions. We designed diagnostic algorithms to account for differences in the spectral properties among anatomic sites (gingiva, buccal mucosa, etc).

Methods:

In vivo reflectance and fluorescence spectra were collected from 71 patients with oral lesions. The tissue was then biopsied and the specimen evaluated by histopathology. Quantitative parameters related to tissue morphology and biochemistry were extracted from the spectra. Diagnostic algorithms specific for combinations of sites with similar spectral properties were developed.

Results:

Discrimination of benign from dysplastic/malignant lesions was most successful when algorithms were designed for individual sites (area under the receiver operator characteristic curve [ROC-AUC], 0.75 for the lateral surface of the tongue) and was least accurate when all sites were combined (ROC-AUC, 0.60). The combination of sites with similar spectral properties (floor of mouth and lateral surface of the tongue) yielded an ROC-AUC of 0.71.

Conclusions:

Accurate spectroscopic detection of oral disease must account for spectral variations among anatomic sites. Anatomy-based algorithms for single sites or combinations of sites demonstrated good diagnostic performance in distinguishing benign lesions from dysplastic/malignant lesions and consistently performed better than algorithms developed for all sites combined.

Predicting recurrent aphthous ulceration using genetic algorithms-optimized neural networks

Objective

To construct and optimize a neural network that is capable of predicting the occurrence of recurrent aphthous ulceration (RAU) based on a set of appropriate input data.

Participants and methods

Artificial neural networks (ANN) software employing genetic algorithms to optimize the architecture neural networks was used. Input and output data of 86 participants (predisposing factors and status of the participants with regards to recurrent aphthous ulceration) were used to construct and train the neural networks. The optimized neural networks were then tested using untrained data of a further 10 participants.

Results

The optimized neural network, which produced the most accurate predictions for the presence or absence of recurrent aphthous ulceration was found to employ: gender, hematological (with or without ferritin) and mycological data of the participants, frequency of tooth brushing, and consumption of vegetables and fruits.

Conclusions

Factors appearing to be related to recurrent aphthous ulceration and appropriate for use as input data to construct ANNs that predict recurrent aphthous ulceration were found to include the following: gender, hemoglobin, serum vitamin B12, serum ferritin, red cell folate, salivary candidal colony count, frequency of tooth brushing, and the number of fruits or vegetables consumed daily.

Discriminant analysis of autofluorescence spectra for classification of oral lesions in vivo

BACKGROUND AND OBJECTIVES

Low survival rate of individuals with oral cancer emphasize the significance of early detection and treatment. Optical spectroscopic techniques are under various stages of development for diagnosis of epithelial neoplasm. This study evaluates the potential of a multivariate statistical algorithm to classify oral mucosa from autofluorescence spectral features recorded in vivo.

STUDY DESIGN/METHODS

Autofluorescence spectra were recorded in a clinical trial from 15 healthy volunteers and 34 patients with diode laser excitation (404 nm) and pre-processed by normalization, mean-scaling and its combination. Linear discriminant analysis (LDA) based on leave-one-out (LOO) method of cross validation was performed on spectral data for tissue characterization. The sensitivity and specificity were determined for different lesion pairs from the scatter plot of discriminant function scores.

RESULTS

Autofluorescence spectra of healthy volunteers consists of a broad emission at 500 nm that is characteristic of endogenous fluorophores, whereas in malignant lesions three additional peaks are observed at 635, 685, and 705 nm due to the accumulation of porphyrins in oral lesions. It was observed that classification design based on discriminant function scores obtained by LDA-LOO method was able to differentiate pre-malignant dysplasia from squamous cell carcinoma (SCC), benign hyperplasia from dysplasia and hyperplasia from normal with overall sensitivities of 86%, 78%, and 92%, and specificities of 90%, 100%, and 100%, respectively.

CONCLUSIONS

The application of LDA-LOO method on the autofluorescence spectra recorded during a clinical trial in patients was found suitable to discriminate oral mucosal alterations during tissue transformation towards malignancy with improved diagnostic accuracies.

Improved diagnosis of oral premalignant lesions in submucous fibrosis patients with 5-aminolevulinic acid induced PpIX fluorescence

We investigate the possibility of using ALA-derived PpIX fluorescence spectroscopy for the detection of epithelial hyperkeratosis (EH) or epithelial dysplasia (ED) lesions in oral submucous fibrosis (OSF) patients that could not be found by autofluorescence spectroscopy. Twenty percent of ALA solution gel was applied onto oral neoplasia and surrounding normal tissue [normal oral mucosa (NOM)] for 90 min. Fluorescence emission spectra were measured under 410 nm excitation. Generally, the most intense fluorescence emission peaks occurred at 460 and 630 nm. The ratios of the area under red peak (630+/-10 nm) to the area under blue peak (460+/-10 nm), denoted as RB, were calculated. We found that OSF mucosa has the lowest RB value, followed by NOM, EH on OSF, and ED on OSF. An ANOVA test showed significant differences between OSF, NOM, EH on OSF, and ED on OSF (p<0.05). However, measurements of autofluorescence (i.e., before ALA application) show no significant differences between OSF, NOM, EH on OSF, and ED on OSF (ANOVA test, p>0.05). These results indicate that ALA-induced PpIX fluorescence spectroscopy could be used to identify the premalignant lesions on oral fibrotic mucosa, which could not be found by autofluorescence.

Noninvasive evaluation of oral lesions using depth-sensitive optical spectroscopy

BACKGROUND

Optical spectroscopy is a noninvasive technique with potential applications for diagnosis of oral dysplasia and early cancer. In this study, we evaluated the diagnostic performance of a depth-sensitive optical spectroscopy (DSOS) system for distinguishing dysplasia and carcinoma from non-neoplastic oral mucosa.

METHODS

Patients with oral lesions and volunteers without any oral abnormalities were recruited to participate. Autofluorescence and diffuse reflectance spectra of selected oral sites were measured using the DSOS system. A total of 424 oral sites in 124 subjects were measured and analyzed, including 154 sites in 60 patients with oral lesions and 270 sites in 64 normal volunteers. Measured optical spectra were used to develop computer-based algorithms to identify the presence of dysplasia or cancer. Sensitivity and specificity were calculated using a gold standard of histopathology for patient sites and clinical impression for normal volunteer sites.

RESULTS

Differences in oral spectra were observed in: (1) neoplastic versus nonneoplastic sites, (2) keratinized versus nonkeratinized tissue, and (3) shallow versus deep depths within oral tissue. Algorithms based on spectra from 310 nonkeratinized anatomic sites (buccal, tongue, floor of mouth, and lip) yielded an area under the receiver operating characteristic curve of 0.96 in the training set and 0.93 in the validation set.

CONCLUSIONS

The ability to selectively target epithelial and shallow stromal depth regions appeared to be diagnostically useful. For nonkeratinized oral sites, the sensitivity and specificity of this objective diagnostic technique were comparable to that of clinical diagnosis by expert observers. Thus, DSOS has potential to augment oral cancer screening efforts in community settings.

Fluorescence spectroscopy of oral tissue: Monte Carlo modeling with site-specific tissue properties

A Monte Carlo model with site-specific input is used to predict depth-resolved fluorescence spectra from individual normal, inflammatory, and neoplastic oral sites. Our goal in developing this model is to provide a computational tool to study how the morphological characteristics of the tissue affect clinically measured spectra. Tissue samples from the measured sites are imaged using fluorescence confocal microscopy; autofluorescence patterns are measured as a function of depth and tissue sublayer for each individual site. These fluorescence distributions are used as input to the Monte Carlo model to generate predictions of fluorescence spectra, which are compared to clinically measured spectra on a site-by-site basis. A lower fluorescence intensity and longer peak emission wavelength observed in clinical spectra from dysplastic and cancerous sites are found to be associated with a decrease in measured fluorescence originating from the stroma or deeper fibrous regions, and an increase in the measured fraction of photons originating from the epithelium or superficial tissue layers. The simulation approach described here can be used to suggest an optical probe design that samples fluorescence at a depth that gives optimal separation in the spectral signal measured for benign, dysplastic, and cancerous oral mucosa.

Understanding the biological basis of autofluorescence imaging for oral cancer detection: high-resolution fluorescence microscopy in viable tissue

PURPOSE

Autofluorescence imaging is increasingly used to noninvasively identify neoplastic oral cavity lesions. Improving the diagnostic accuracy of these techniques requires a better understanding of the biological basis for optical changes associated with neoplastic transformation in oral tissue.

EXPERIMENTAL DESIGN

A total of 49 oral biopsies were considered in this study. The autofluorescence patterns of viable normal, benign, and neoplastic oral tissue were imaged using high-resolution confocal fluorescence microscopy.

RESULTS

The autofluorescence properties of oral tissue vary significantly based on anatomic site and pathologic diagnosis. In normal oral tissue, most of the epithelial autofluorescence originates from the cytoplasm of cells in the basal and intermediate regions, whereas structural fibers are responsible for most of the stromal fluorescence. A strongly fluorescent superficial layer was observed in tissues from the palate and the gingiva, which contrasts with the weakly fluorescent superficial layer found in other oral sites. Upon UV excitation, benign inflammation shows decreased epithelial fluorescence, whereas dysplasia displays increased epithelial fluorescence compared with normal oral tissue. Stromal fluorescence in both benign inflammation and dysplasia drops significantly at UV and 488 nm excitation.

CONCLUSION

Imaging oral lesions with optical devices/probes that sample mostly stromal fluorescence may result in a similar loss of fluorescence intensity and may fail to distinguish benign from precancerous lesions. Improved diagnostic accuracy may be achieved by designing optical probes/devices that distinguish epithelial fluorescence from stromal fluorescence and by using excitation wavelengths in the UV range.

Probing local tissue changes in the oral cavity for early detection of cancer using oblique polarized reflectance spectroscopy: a pilot clinical trial

We report the results of an oral cavity pilot clinical trial to detect early precancer and cancer using a fiber optic probe with obliquely oriented collection fibers that preferentially probe local tissue morphology and heterogeneity using oblique polarized reflectance spectroscopy (OPRS). We extract epithelial cell nuclear sizes and 10 spectral features. These features are analyzed independently and in combination to assess the best metrics for separation of diagnostic classes. Without stratifying the data according to anatomical location or level of keratinization, OPRS is found to be sensitive to four diagnostic categories: normal, benign, mild dysplasia, high-grade dysplasia, and carcinoma. Using linear discriminant analysis, separation of normal from high-grade dysplasia and carcinoma yield a sensitivity and specificity of 90 and 86%, respectively. Discrimination of morphologically similar lesions such as normal from mild dysplasia is achieved with a sensitivity of 75% and specificity of 73%. Separation of visually indistinguishable benign lesions from high-grade dysplasia and carcinoma is achieved with good sensitivity (100%) and specificity (85%), while separation of benign from mild dysplasia gives a sensitivity of 92% and a specificity of 69%. These promising results suggest that OPRS has the potential to aid screening and diagnosis of oral precancer and cancer.

Fluoroquinolone antibiotics having the potential to interfere with fluorescence-based diagnosis

Fluorescence, both intrinsic and exogenously induced, is being used for diagnosis of abnormal tissue. Excitation wavelengths used by these methods range from 320 to 450 nm. The presence of absorbing or fluorescing drugs is rarely taken into account by practitioners of fluorescence diagnosis and has the potential to yield false-positive or false-negative results. Our aim is to quantify this potential by (1) comparing the quantum yield of fluoroquinolone antibiotics to those of known tissue fluorophores and (2) taking into account drug concentrations in the tissue during treatment. Quantum yields are determined relative to a working standard of Rhodamine 6G in ethanol. The working standard was calibrated against a fluorescein standard. We concentrated our initial efforts on (1) the fluoroquinolone antibiotics, ciprofloxacin, norfloxacin and ofloxacin and (2) the intrinsic tissue fluorophores, NADH, FAD and protoporphyrin IX. When ciprofloxacin, norfloxacin and ofloxacin were excited at wavelengths 310-390 nm, emission occurred from 350 to 650 nm with quantum yields ranging from 0.03 to 0.3. Quantum yields for intrinsic fluorophores excited at their peak absorption wavelengths were 0.02 (NADH, 340 nm), 0.035 (FAD, 450 nm) and 0.087 (protoporphyrin IX, 408 nm). A review of the literature shows that these fluoroquinolones have a large volume of distribution and can be found in high concentrations in almost every organ during a treatment regimen. The product of the drug tissue concentration and quantum yield, which we term the fluorescence effective concentration, is such that it is likely these fluoroquinolones will interfere during fluorescence diagnosis techniques.

The prediction of total anthocyanin concentration in red-grape homogenates using visible-near-infrared spectroscopy and artificial neural networks

This study compares the performance of partial least squares (PLS) regression analysis and artificial neural networks (ANN) for the prediction of total anthocyanin concentration in red-grape homogenates from their visible-near-infrared (Vis-NIR) spectra. The PLS prediction of anthocyanin concentrations for new-season samples from Vis-NIR spectra was characterised by regression non-linearity and prediction bias. In practice, this usually requires the inclusion of some samples from the new vintage to improve the prediction. The use of WinISI LOCAL partly alleviated these problems but still resulted in increased error at high and low extremes of the anthocyanin concentration range. Artificial neural networks regression was investigated as an alternative method to PLS, due to the inherent advantages of ANN for modelling non-linear systems. The method proposed here combines the advantages of the data reduction capabilities of PLS regression with the non-linear modelling capabilities of ANN. With the use of PLS scores as inputs for ANN regression, the model was shown to be quicker and easier to train than using raw full-spectrum data. The ANN calibration for prediction of new vintage grape data, using PLS scores as inputs, was more linear and accurate than global and LOCAL PLS models and appears to reduce the need for refreshing the calibration with new-season samples. ANN with PLS scores required fewer inputs and was less prone to overfitting than using PCA scores. A variation of the ANN method, using carefully selected spectral frequencies as inputs, resulted in prediction accuracy comparable to those using PLS scores but, as for PCA inputs, was also prone to overfitting with redundant wavelengths.

Fluorescence spectroscopy and birefringence of molecular changes in maturing rat tail tendon

Tissue remodeling during maturation, wound healing, and response to vascular stress involves molecular changes of collagen and elastin in the extracellular matrix (ECM). Two optical techniques are effective for investigating these changes--laser-induced fluorescence (LIF) spectroscopy and polarizing microscopy. LIF spectroscopy integrates the signal from both elastin and collagen cross-linked structure, whereas birefringence is a measure of only collagen. Our purpose is (1) to evaluate the rat tail tendon (RTT) spectroscopy against data from purified extracted protein standards and (2) to correlate the two optical techniques in the study of RTT and skin. Spectra from tissue samples from 27 male rats and from extracted elastin and collagen were obtained using LIF spectroscopy (357 nm). Birefringence was measured on 5-mum histological sections of the same tissue. Morphometric analysis reveals that elastin represents approximately 10% of tendon volume and contributes to RTT fluorescence. RTT maximum fluorescence emission intensity (FEI(max)), which includes collagen and elastin, increases with animal weight (R(2)=0.64). Birefringence, when plotted against weight, increases to a plateau (nonlinear correlation: R(2)=0.90), tendon having greater birefringence than skin. LIF spectroscopy and collagen fiber birefringence are shown to provide complementary measurements of molecular structure (tendon birefringence versus FEI(max) at R(2)=0.60).

Optical pathology using oral tissue fluorescence spectra: classification by principal component analysis and k-means nearest neighbor analysis

The spectral analysis and classification for discrimination of pulsed laser-induced autofluorescence spectra of pathologically certified normal, premalignant, and malignant oral tissues recorded at a 325-nm excitation are carried out using MATLAB@R6-based principal component analysis (PCA) and k-means nearest neighbor (k-NN) analysis separately on the same set of spectral data. Six features such as mean, median, maximum intensity, energy, spectral residuals, and standard deviation are extracted from each spectrum of the 60 training samples (spectra) belonging to the normal, premalignant, and malignant groups and they are used to perform PCA on the reference database. Standard calibration models of normal, premalignant, and malignant samples are made using cluster analysis. We show that a feature vector of length 6 could be reduced to three components using the PCA technique. After performing PCA on the feature space, the first three principal component (PC) scores, which contain all the diagnostic information, are retained and the remaining scores containing only noise are discarded. The new feature space is thus constructed using three PC scores only and is used as input database for the k-NN classification. Using this transformed feature space, the centroids for normal, premalignant, and malignant samples are computed and the efficient classification for different classes of oral samples is achieved. A performance evaluation of k-NN classification results is made by calculating the statistical parameters specificity, sensitivity, and accuracy and they are found to be 100, 94.5, and 96.17%, respectively.

Early Diagnosis of Oral Cavity Cancers

Dentists, primary care physicians, and otolaryngologists should continue to perform complete oral cavity examinations and should be aware of high-risk populations for oral cavity carcinomas. Oral cavity carcinoma is the sixth most common cancer and is often detected in later stages. By using the modalities of physical examination, brush biopsies, vital staining, and spectral analysis, it is hoped that more cancers will be detected at an early stage, decreasing the morbidity and mortality of oral cavity tumors.

The status of in vivo autofluorescence spectroscopy and imaging for oral oncology

Autofluorescence spectroscopy and imaging have been studied for the early detection and classification of (pre)malignancies of the oral mucosa. In the present review we will give an overview of the literature on autofluorescence imaging and spectroscopy for various clinical questions. From the studies performed so far we hope to conclude whether autofluorescence spectroscopy and imaging are helpful in the diagnosis of lesions of the oral mucosa, and if this is the case: for which clinical questions they are suitable. A strong emphasis is put on in vivo human studies of the oral mucosa.

Biophotonic and Other Physical Methods for Characterizing Oral Mucosa

This article discusses biophotonic and other physical methods for characterizing oral mucosa.

Autofluorescence and diffuse reflectance spectroscopy for oral oncology

BACKGROUND AND OBJECTIVES

Autofluorescence and diffuse reflectance spectroscopy have been used separately and combined for tissue diagnostics. Previously, we assessed the value of autofluorescence spectroscopy for the classification of oral (pre-)malignancies. In the present study, we want to determine the contributions of diffuse reflectance and autofluorescence spectroscopy to diagnostic performance.

STUDY DESIGN/MATERIALS AND METHODS

Autofluorescence and diffuse reflectance spectra were recorded from 172 oral lesions and 70 healthy volunteers. Autofluorescence spectra were corrected in first order for blood absorption effects using diffuse reflectance spectra. Principal Components Analysis (PCA) with various classifiers was applied to distinguish (1) cancer and (2) all lesions from healthy oral mucosa, and (3) dysplastic and malignant lesions from benign lesions. Autofluorescence and diffuse reflectance spectra were evaluated separately and combined.

RESULTS

The classification of cancer versus healthy mucosa gave excellent results for diffuse reflectance as well as corrected autofluorescence (Receiver Operator Characteristic (ROC) areas up to 0.98). For both autofluorescence and diffuse reflectance spectra, the classification of lesions versus healthy mucosa was successful (ROC areas up to 0.90). However, the classification of benign and (pre-)malignant lesions was not successful for raw or corrected autofluorescence spectra (ROC areas <0.70). For diffuse reflectance spectra, the results were slightly better (ROC areas up to 0.77).

CONCLUSIONS

The results for plain and corrected autofluorescence as well as diffuse reflectance spectra were similar. The relevant information for distinguishing lesions from healthy oral mucosa is probably sufficiently contained in blood absorption and scattering information, as well as in corrected autofluorescence. However, neither type of information is capable of distinguishing benign from dysplastic and malignant lesions. Combining autofluorescence and reflectance only slightly improved the results.

Time-resolved autofluorescence spectroscopy for classifying normal and premalignant oral tissues

BACKGROUND AND OBJECTIVES

Time-resolved autofluorescence spectroscopy has been used for effectively distinguishing normal tissues from precancers and cancers in various organs. The aim of this study was to find out the possibility of using time-resolved autofluorescence spectroscopy to differentiate normal oral mucosa (NOM) from oral premalignant lesions including verrucous hyperplasia (VH), epithelial hyperplasia (EH), and epithelial dysplasia (ED).

STUDY DESIGN/MATERIALS AND METHODS

Time-resolved autofluorescence spectra at 633 nm under 410-nm excitation were recorded for 15 VH, 9 EH, 14 ED, and 38 NOM samples. The two-component lifetimes of the obtained curves were calculated, and a Fisher's discriminant analysis (FDA) was employed for distinguishing these tissue samples.

RESULTS

After two-component lifetimes for all samples being calculated, a two-dimensional scatter plot was developed, in which 76 oral tissue samples were separated into three groups by FDA. With a leave-one-out method, the FDA algorithm gave an accuracy rate of 93% for ED, of 75% for VH and EH, and of 100% for NOM samples. In addition, all oral premalignant lesions (including VH, EH, and ED) could be distinguished from NOM samples by this FDA algorithm.

CONCLUSIONS

We conclude that time-resolved autofluorescence spectroscopy at 633 nm under 410-nm excitation, based on two-component lifetime calculation and FDA, is a very sensitive technique for in vivo diagnosis of oral premalignant lesions. .

Effects of individual characteristics on healthy oral mucosa autofluorescence spectra

Autofluorescence spectroscopy is a tool for detecting tissue alterations in vivo. In a previous study, we found spectral differences between clinically normal mucosa of different patient groups. These are possibly caused by associated patient characteristics. In the present study, we explore the influences of volunteer characteristics on healthy oral mucosa autofluorescence. Autofluorescence spectra were recorded in 96 volunteers with no clinically observable oral lesions. We applied principal components analysis to extract the relevant information. We used multivariate linear regression techniques to estimate the effect of volunteer characteristics on principal component scores. Statistically significant differences were found for all factors but age. Skin color strongly affected autofluorescence intensity. Gender differences were found in blood absorption. Alcohol consumption was associated with porphyrin-like peaks. However, all differences but those associated with skin color were of the same order of magnitude as standard deviations within categories. The effects of volunteer characteristics on autofluorescence spectra of the oral mucosa are measurable. Only the effects of skin color were large. Therefore, in lesion classification, skin color should be taken into account.

Clinical study for classification of benign, dysplastic, and malignant oral lesions using autofluorescence spectroscopy

Autofluorescence spectroscopy shows promising results for detection and staging of oral (pre-)malignancies. To improve staging reliability, we develop and compare algorithms for lesion classification. Furthermore, we examine the potential for detecting invisible tissue alterations. Autofluorescence spectra are recorded at six excitation wavelengths from 172 benign, dysplastic, and cancerous lesions and from 97 healthy volunteers. We apply principal components analysis (PCA), artificial neural networks, and red/green intensity ratio's to separate benign from (pre-)malignant lesions, using four normalization techniques. To assess the potential for detecting invisible tissue alterations, we compare PC scores of healthy mucosa and surroundings/contralateral positions of lesions. The spectra show large variations in shape and intensity within each lesion group. Intensities and PC score distributions demonstrate large overlap between benign and (pre-)malignant lesions. The receiver-operator characteristic areas under the curve (ROC-AUCs) for distinguishing cancerous from healthy tissue are excellent (0.90 to 0.97). However, the ROC-AUCs are too low for classification of benign versus (pre-)malignant mucosa for all methods (0.50 to 0.70). Some statistically significant differences between surrounding/contralateral tissues of benign and healthy tissue and of (pre-)malignant lesions are observed. We can successfully separate healthy mucosa from cancers (ROC-AUC>0.9). However, autofluorescence spectroscopy is not able to distinguish benign from visible (pre-)malignant lesions using our methods (ROC-AUC<0.65). The observed significant differences between healthy tissue and surroundings/contralateral positions of lesions might be useful for invisible tissue alteration detection.